this is based on calsyslab project
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 

175 lines
7.0 KiB

__author__ = 'DarkWeb'
# Here, we are importing the auxiliary functions to clean or convert data
from MarketPlaces.Utilities.utilities import *
# Here, we are importing BeautifulSoup to search through the HTML tree
from bs4 import BeautifulSoup, ResultSet, Tag
def anonymousMarketplace_description_parser(soup: Tag):
# Fields to be parsed
vendor = "-1" # 0 *Vendor_Name
success = "-1" # 1 Vendor_Successful_Transactions
rating_vendor = "-1" # 2 Vendor_Rating
name = "-1" # 3 *Product_Name
describe = "-1" # 4 Product_Description
CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures)
MS = "-1" # 6 Product_MS_Classification (Microsoft Security)
category = "-1" # 7 Product_Category
views = "-1" # 8 Product_Number_Of_Views
reviews = "-1" # 9 Product_Number_Of_Reviews
rating_item = "-1" # 10 Product_Rating
addDate = "-1" # 11 Product_AddedDate
BTC = "-1" # 12 Product_BTC_SellingPrice
USD = "-1" # 13 Product_USD_SellingPrice
EURO = "-1" # 14 Product_EURO_SellingPrice
sold = "-1" # 15 Product_QuantitySold
left = "-1" # 16 Product_QuantityLeft
shipFrom = "-1" # 17 Product_ShippedFrom
shipTo = "-1" # 18 Product_ShippedTo
product_name = soup.find("h1", {"class": "product_title entry-title"}).text
name = cleanString(product_name.strip())
product_description_list: ResultSet[Tag] = soup.find("div", {"id": "tab-description"}).find_all("div")
describe_output = ""
for div in product_description_list:
describe_output += div.text
describe = cleanString(describe_output.strip())
product_ratings: Tag = soup.find("div", {"class": "woocommerce-product-rating"})
product_reviews = product_ratings.find("span", {"class": "rating"}).text
reviews = cleanString(product_reviews.strip())
product_star_rating = product_ratings.find("strong", {"class": "rating"}).text
rating_item = cleanString(product_star_rating.strip())
product_price = soup.find("span", {"class": "woocommerce-Price-amount amount"}).text
USD = cleanString(product_price.replace("$", "").strip())
# Populating the final variable (this should be a list with all fields scraped)
row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate,
BTC, USD, EURO, sold, left, shipFrom, shipTo)
# Sending the results
return row
def anonymousMarketplace_listing_parser(soup: Tag):
# Fields to be parsed
nm = 0 # *Total_Products (Should be Integer)
mktName = "AnonymousMarketplace" # 0 *Marketplace_Name
vendor = [] # 1 *Vendor y
rating_vendor = [] # 2 Vendor_Rating
success = [] # 3 Vendor_Successful_Transactions
name = [] # 4 *Product_Name y
CVE = [] # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures)
MS = [] # 6 Product_MS_Classification (Microsoft Security)
category = [] # 7 Product_Category y
describe = [] # 8 Product_Description
views = [] # 9 Product_Number_Of_Views
reviews = [] # 10 Product_Number_Of_Reviews
rating_item = [] # 11 Product_Rating
addDate = [] # 12 Product_AddDate
BTC = [] # 13 Product_BTC_SellingPrice
USD = [] # 14 Product_USD_SellingPrice y
EURO = [] # 15 Product_EURO_SellingPrice
sold = [] # 16 Product_QuantitySold
qLeft =[] # 17 Product_QuantityLeft
shipFrom = [] # 18 Product_ShippedFrom
shipTo = [] # 19 Product_ShippedTo
href = [] # 20 Product_Links
woo = soup.find('div', {"class": "woocommerce"})
product_list = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li')
for item in product_list:
item_href = item.find("a", recursive=False).get("href")
href.append(item_href)
item_name = item.find("h2").text
name.append(cleanString(item_name.strip()))
item_rating = item.find("div", {"class": "star-rating"}).find("strong", {"class": "rating"}).text
rating_item.append(cleanString(item_rating.strip()))
try:
item_price = item.find("span", {"class": "woocommerce-Price-amount amount"}).text
item_price = item_price.replace("$", "").strip()
USD.append(cleanNumbers(item_price))
except AttributeError:
USD.append("-1")
vendor.append("AnonymousMarketplace")
rating_vendor.append("-1")
success.append("-1")
CVE.append("-1")
MS.append("-1")
category.append("-1")
describe.append("-1")
views.append("-1")
reviews.append("-1")
addDate.append("-1")
BTC.append("-1")
EURO.append("-1")
sold.append("-1")
qLeft.append("-1")
shipFrom.append("-1")
shipTo.append("-1")
nm += 1
return organizeProducts(
marketplace=mktName,
nm=nm,
vendor=vendor,
rating_vendor=rating_vendor,
success_vendor=success,
nombre=name,
CVE=CVE,
MS=MS,
category=category,
describe=describe,
views=views,
reviews=reviews,
rating_item=rating_item,
addDate=addDate,
BTC=BTC,
USD=USD,
EURO=EURO,
sold=sold,
qLeft=qLeft,
shipFrom=shipFrom,
shipTo=shipTo,
href=href
)
#called by the crawler to get description links on a listing page
#@param: beautifulsoup object that is using the correct html page (listing page)
#return: list of description links from a listing page
def anonymous_links_parser(soup):
# Returning all links that should be visited by the Crawler
href = []
woo = soup.find('div', {"class": "woocommerce"})
listing = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li')
for a in listing:
bae = a.find('a', href=True, recursive=False)
link = bae['href']
href.append(link)
return href